docs: improve SEO metadata across docs pages

docs/components/llms/config.mdx

@@ -1,6 +1,6 @@
 ---
 title: Configurations
-description: "Reference for LLM configuration options in Mem0 for Python and TypeScript, including value precedence rules."
+description: "Reference for Mem0 LLM configuration keys in Python and TypeScript, covering provider precedence, environment variables, and per-provider parameters."
 ---
 
 ## How to define configurations?

docs/components/llms/models/anthropic.mdx

@@ -1,6 +1,6 @@
 ---
 title: Anthropic
-description: "Configure Anthropic Claude models as the LLM provider in Mem0 with API key setup and usage examples."
+description: "Use Anthropic Claude models such as claude-sonnet-4-6 as your Mem0 LLM with the ANTHROPIC_API_KEY, plus temperature and max token controls."
 ---
 
 

docs/components/llms/models/aws_bedrock.mdx

@@ -1,6 +1,6 @@
 ---
 title: AWS Bedrock
-description: "Configure AWS Bedrock as an LLM provider in Mem0 with IAM authentication and Claude model support."
+description: "Run Claude and other Bedrock LLMs in Mem0 using boto3 or the AWS SDK Converse API, with IAM credentials and cross-region inference profile support."
 ---
 
 ### Setup

docs/components/llms/models/azure_openai.mdx

@@ -1,6 +1,6 @@
 ---
 title: Azure OpenAI
-description: "Configure Azure OpenAI as an LLM provider in Mem0 with Azure Identity authentication and deployment settings."
+description: "Use Azure OpenAI deployments as a Mem0 LLM with API key or Azure Identity auth, including the azure_openai_structured provider for structured output."
 ---
 
 <Note> Mem0 Now Supports Azure OpenAI Models in TypeScript SDK </Note>

docs/components/llms/models/deepseek.mdx

@@ -1,6 +1,6 @@
 ---
 title: DeepSeek
-description: "Configure DeepSeek as an LLM provider in Mem0 with API key setup and optional custom endpoint configuration."
+description: "Use DeepSeek chat models such as deepseek-chat as a Mem0 LLM with the DEEPSEEK_API_KEY and an optional DEEPSEEK_API_BASE custom endpoint URL."
 ---
 
 To use DeepSeek LLM models, you have to set the `DEEPSEEK_API_KEY` environment variable. You can also optionally set `DEEPSEEK_API_BASE` if you need to use a different API endpoint (defaults to "https://api.deepseek.com").

docs/components/llms/models/google_AI.mdx

@@ -1,6 +1,6 @@
 ---
 title: Google AI
-description: "Configure Google Gemini as an LLM provider in Mem0 using the google.genai SDK and GOOGLE_API_KEY variable."
+description: "Use Google Gemini models like gemini-2.0-flash-001 as a Mem0 LLM through the new google.genai SDK with the GOOGLE_API_KEY environment variable."
 ---
 
 To use the Gemini model, set the `GOOGLE_API_KEY` environment variable. You can obtain the Google/Gemini API key from [Google AI Studio](https://aistudio.google.com/app/apikey).

docs/components/llms/models/groq.mdx

@@ -1,6 +1,6 @@
 ---
 title: Groq
-description: "Configure Groq as an LLM provider in Mem0 for high-speed inference using LPU-powered language models."
+description: "Use Groq LPU-hosted models such as llama-3.3-70b-versatile as a Mem0 LLM for very low-latency inference with the GROQ_API_KEY environment variable."
 ---
 
 [Groq](https://groq.com/) is the creator of the world's first Language Processing Unit (LPU), providing exceptional speed performance for AI workloads running on their LPU Inference Engine.

docs/components/llms/models/langchain.mdx

@@ -1,6 +1,6 @@
 ---
 title: LangChain
-description: "Use LangChain as an LLM provider in Mem0 to integrate with various chat models through a unified interface."
+description: "Wire LangChain ChatOpenAI, ChatAnthropic, and other chat model classes into Mem0 as the LLM provider to reuse existing LangChain integrations."
 ---
 
 

docs/components/llms/models/litellm.mdx

@@ -1,6 +1,6 @@
 ---
 title: "LiteLLM"
-description: "Use LiteLLM as an LLM provider in Mem0 to access over 100 language models through a unified interface."
+description: "Route Mem0 through LiteLLM to reach 100+ providers via one API in Python, or a LiteLLM proxy at LITELLM_API_BASE from the TypeScript SDK."
 ---
 [Litellm](https://litellm.vercel.app/docs/) is compatible with over 100 large language models (LLMs), all using a standardized input/output format. You can explore the [available models](https://litellm.vercel.app/docs/providers) to use with Litellm. Ensure you set the `API_KEY` for the model you choose to use.
 

docs/components/llms/models/lmstudio.mdx

@@ -1,6 +1,6 @@
 ---
 title: LM Studio
-description: "Configure LM Studio as an LLM provider in Mem0 for running local language models via an OpenAI-compatible API."
+description: "Run local GGUF models in Mem0 via LM Studio server on localhost:1234 using its OpenAI-compatible API, with optional lmstudio_response_format schema."
 ---
 
 To use LM Studio with Mem0, you'll need to have LM Studio running locally with its server enabled. LM Studio provides a way to run local LLMs with an OpenAI-compatible API.

docs/components/llms/models/minimax.mdx

@@ -1,6 +1,6 @@
 ---
 title: MiniMax
-description: "Configure MiniMax as an LLM provider in Mem0 with API key setup and optional custom endpoint configuration."
+description: "Use MiniMax chat models like MiniMax-M2.7 as a Mem0 LLM with the MINIMAX_API_KEY and an optional MINIMAX_API_BASE custom endpoint override."
 ---
 
 To use MiniMax LLM models, you have to set the `MINIMAX_API_KEY` environment variable. You can also optionally set `MINIMAX_API_BASE` if you need to use a different API endpoint (defaults to "https://api.minimax.io/v1").

docs/components/llms/models/mistral_AI.mdx

@@ -1,6 +1,6 @@
 ---
 title: Mistral AI
-description: "Configure Mistral AI as an LLM provider in Mem0 using the litellm integration and Mixtral model family."
+description: "Use Mistral AI models such as open-mixtral-8x7b as a Mem0 LLM through the litellm provider with the MISTRAL_API_KEY environment variable."
 ---
 
 To use mistral's models, please obtain the Mistral AI api key from their [console](https://console.mistral.ai/). Set the `MISTRAL_API_KEY` environment variable to use the model as given below in the example.

docs/components/llms/models/ollama.mdx

@@ -1,6 +1,6 @@
 ---
 title: Ollama
-description: "Configure Ollama as an LLM provider in Mem0 for running local language models with tool-calling support."
+description: "Run local Ollama LLMs such as mixtral:8x7b or llama3.1:8b as a Mem0 provider with tool calling support and a configurable Ollama server URL."
 ---
 
 You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.com/search?c=tools) support tool calling.

docs/components/llms/models/openai.mdx

@@ -1,6 +1,6 @@
 ---
 title: OpenAI
-description: "Configure OpenAI as an LLM provider in Mem0 with support for GPT models and Openrouter compatibility."
+description: "Use OpenAI GPT models like gpt-5-mini as a Mem0 LLM with OPENAI_API_KEY, plus optional Openrouter routing and the openai_structured output mode."
 ---
 
 To use OpenAI LLM models, you have to set the `OPENAI_API_KEY` environment variable. You can obtain the OpenAI API key from the [OpenAI Platform](https://platform.openai.com/account/api-keys).

docs/components/llms/models/sarvam.mdx

@@ -1,6 +1,6 @@
 ---
 title: Sarvam AI
-description: "Configure Sarvam AI as an LLM provider in Mem0, specializing in Indian language support with the Sarvam-M model."
+description: "Use Sarvam AI models like sarvam-m as a Mem0 LLM for Indian language conversations, with reasoning_effort, frequency_penalty, and seed controls."
 ---
 
 **Sarvam AI** is an Indian AI company developing language models with a focus on Indian languages and cultural context. Their latest model **Sarvam-M** is designed to understand and generate content in multiple Indian languages while maintaining high performance in English.

docs/components/llms/models/together.mdx

@@ -1,6 +1,6 @@
 ---
 title: Together
-description: "Configure Together AI as an LLM provider in Mem0 with API key setup and optional custom endpoint configuration."
+description: "Use Together AI hosted models such as MiniMaxAI/MiniMax-M3 as a Mem0 LLM with the TOGETHER_API_KEY and an optional TOGETHER_API_BASE endpoint."
 ---
 
 To use Together LLM models, you have to set the `TOGETHER_API_KEY` environment variable. You can obtain the Together API key from their [Account settings page](https://api.together.ai/settings/projects/~current/api-keys).

docs/components/llms/models/vllm.mdx

@@ -1,6 +1,6 @@
 ---
 title: vLLM
-description: "Configure vLLM as an LLM provider in Mem0 for high-performance local inference with GPU-optimized serving."
+description: "Serve local models like Qwen2.5-32B-Instruct through a vLLM server and connect Mem0 to it via VLLM_BASE_URL for fast, GPU-optimized inference."
 ---
 
 [vLLM](https://docs.vllm.ai/) is a high-performance inference engine for large language models that provides significant performance improvements for local inference. It's designed to maximize throughput and memory efficiency for serving LLMs.

docs/components/llms/models/xAI.mdx

@@ -1,6 +1,6 @@
 ---
 title: xAI
-description: "Configure xAI Grok models as an LLM provider in Mem0 with API key setup and usage examples."
+description: "Use xAI Grok models such as grok-4.3 as a Mem0 LLM with the XAI_API_KEY, plus an optional XAI_API_BASE for custom endpoint routing."
 ---
 
 [xAI](https://x.ai/) is a new AI company founded by Elon Musk that develops large language models, including Grok. Grok is trained on real-time data from X (formerly Twitter) and aims to provide accurate, up-to-date responses with a touch of wit and humor.

docs/components/llms/overview.mdx

@@ -1,6 +1,6 @@
 ---
 title: Overview
-description: "Overview of all supported LLM providers in Mem0, including OpenAI, Anthropic, Groq, Ollama, and more."
+description: "Compare Mem0 LLM providers including OpenAI, Anthropic, Groq, Ollama, Together, Mistral, Gemini, Bedrock, DeepSeek, xAI, Sarvam, and LangChain."
 ---
 
 Mem0 includes built-in support for various popular large language models. Memory can utilize the LLM provided by the user, ensuring efficient use for specific needs.